Dave Willner

We just released a Zentropi skill that lets your AI agent build its own content classifiers. You describe what you want to catch, it writes the initial policy, benchmarks it on real samples, and ships a working labeler - accurate, cheap, and fast! Install it at github.com/zent…

GitHub - zentropi-ai/skills: Agent skills powered by the Zentropi content classification engine github.com

@samidh.bsky.social and I are releasing CoPE-B today, the next version of our policy-adaptive content classifier. It delivers at-or-better-than-frontier classification while being self-hostable, faster, and cheaper to run. Full writeup with benchmarks at blog.zentropi.ai/meet-…

Meet CoPE-B: Frontier-Quality Content Classification You Can Self-Host blog.zentropi.ai

At TrustCon this year I talked about a technique we’ve developed for automatically optimizing content-moderation policies, using an inversion of the binocular labeling approach Zentropi had already pioneered. Today we're shipping the tool that technique became. blog.zentropi.a…

Optimizing our Policy Optimizers blog.zentropi.ai

Making impossible safety challenges tractable is a lot of why we built Zentropi. Today @vaishnavi.bsky.social shipped a great example of what that means in practice - a set of open-source self-harm and suicide policies for teens: quire.substack.com/p/what-it-takes-for-llms-to-…

[What it Takes] For LLMs to Make Age-Appropriate Content Policies Enforceable quire.substack.com